Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code descriptions and tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵↵
    0.45
    ↵↵↵↵↵
    0.42
    ocles
    0.42
     Gloria
    0.40
    buy
    0.39
    ↵↵↵↵
    0.39
    parking
    0.39
    ↵
    0.39
     tavern
    0.38
     Stay
    0.38
    POSITIVE LOGITS
     பயன்படுத்து
    0.47
     precondition
    0.47
    LuaPush
    0.45
     hyperparameters
    0.45
     equilibration
    0.44
     univariate
    0.44
    )=\
    0.44
     Universidade
    0.44
     $=\
    0.43
     LPTMR
    0.43
    Act Density 0.003%

    No Known Activations